Robust fuzzy factorization machine with noise clustering-based membership function estimation

Abstract

Factorization machine (FM) is a promising model-based algorithm for collaborative filtering (CF), but can bring inferior performances if datasets include users having low confidence. In this paper, a robust FM model is proposed by introducing the noise clustering-based noise rejection mechanism into Fuzzy FM, which utilizes fuzzy memberships of users for considering the responsibility of each user in FM modeling. By automatically updating fuzzy memberships with user-wise criteria of prediction errors, the FM model is better fitted to reliable users and is expected to improve the generalization ability for predicting the preference degrees of unknown items. The characteristics of the proposed method are demonstrated through numerical experiments with MovieLens movie evaluation data such that the prediction ability for not only the training ratings but also the test ratings of reliable users can be improved by carefully tuning the noise sensitivity weight.